Medical vulnerability event reporting method and device

Abstract

The invention relates to a medical vulnerability event reporting method and device, relates to the technical field of computer intelligent computing, and aims to predict whether an illness state is further developed or not according to currently recorded illness state data so as to avoid serious consequences caused by vulnerability events. The method comprises the steps that in the process of reading system records, it is detected that illness state key information associated with a target event exists in a first medical event, and the illness state key information is input into a preset medical event vulnerability evaluation model; the target event comprises development from the first medical event to the second medical event; calculating the target event in a first dimension and a second dimension by using a medical event vulnerability evaluation model to obtain a calculation result; the first dimension comprises the probability that the first medical event develops to the second medical event; the second dimension comprises consequences caused by development of the first medical event to the second medical event; and reporting the target event to a processing port corresponding to the second medical event according to the calculation result.

Description

Technical Field

[0001] The present application relates to the field of computer intelligent computing technology, and in particular to a method and device for reporting medical vulnerability events. Background Art

[0002] In order to share modern information in hospitals (for medical information sharing), so that each department and hospital can make full use of limited medical and health information, the existing technology has set up an information system that can carry out collaborative medical services as a support. This system is called the Hospital Information System (HIS). However, the existing medical information system can only record and analyze the existing conditions, symptoms, diagnosis records, medication methods, and treatment methods, and timely discover and predict the further development of the condition. There is still room for improvement, and timely measures to avoid and prevent the progression of the condition need to be taken. Summary of the invention

[0003] The medical vulnerability event reporting method of this application predicts whether the disease condition will further develop based on the currently recorded disease data, calculates the consequences based on the possible development of the disease condition, and reports the consequences caused by the development of the disease condition to the department with problem-solving capabilities to avoid serious consequences caused by the occurrence of vulnerability events.

[0004] In a first aspect, an embodiment provides a method for reporting a medical vulnerability event, the method comprising: in the process of reading system records, detecting the presence of key information of a medical condition associated with a target event in a first medical event, and inputting the key information of the medical condition into a pre-set medical event vulnerability assessment model; the target event comprises the development of the first medical event to a second medical event; using the medical event vulnerability assessment model to calculate the target event in a first dimension and a second dimension to obtain a calculation result; the first dimension comprises the probability of the first medical event developing to the second medical event; the second dimension comprises the consequences caused by the development of the first medical event to the second medical event; according to the calculation result, reporting the target event to the processing port corresponding to the second medical event.

[0005] In one embodiment, the target event is calculated in the first dimension and the second dimension using the medical event vulnerability assessment model to obtain a calculation result, including: Determining the probability of the target event occurring due to the key disease information based on the medical event vulnerability assessment model; Determining the extent of loss caused by the occurrence of the second medical event based on the medical event vulnerability assessment model; According to the calculation result, reporting the target event to a processing port corresponding to the second medical event includes: If the probability of the target event occurring due to the critical disease information is greater than a first preset threshold, reporting the target event to the second medical event corresponding processing port; If the degree of loss caused by the occurrence of the second medical event is greater than a second preset threshold, the target event is reported to the processing port corresponding to the second medical event.

[0006] In one embodiment, determining the probability of the target event occurring within at least one recording period due to the critical condition information based on the medical event vulnerability assessment model includes: If it is found in the medical event vulnerability assessment model that the average probability is lower than the first preset threshold and greater than the third preset threshold, the average probability is increased to exceed the first preset threshold.

[0007] In one embodiment, the target event is calculated in the first dimension and the second dimension using the medical event vulnerability assessment model to obtain a calculation result, including: Determining the probability of the target event occurring due to the key disease information based on the medical event vulnerability assessment model; Determining the extent of loss caused by the occurrence of the second medical event based on the medical event vulnerability assessment model; Predicting the risk level of the target event according to the probability of the target event occurring and the extent of the loss caused by the occurrence of the second medical event; According to the calculation result, reporting the target event to a processing port corresponding to the second medical event includes: According to the risk level, the target event is reported to the processing port corresponding to the second medical event.

[0008] In one embodiment, determining the extent of loss caused by the occurrence of the second medical event based on the medical event vulnerability assessment model includes: Finding the direct calculation corresponding to the occurrence of the target event in the medical event vulnerability assessment model, or / and querying the operation means corresponding to the second medical event; Calculate the degree of loss corresponding to the operation means.

[0009] In one embodiment, before predicting the risk level of the target event based on the probability of the target event occurring within at least one recording period and the degree of loss caused by the occurrence of the second medical event, the method further includes: quantifying the first dimension and the second dimension according to development records of different medical events stored in the medical event vulnerability assessment model; Predicting the risk level of the target event according to the probability of the target event occurring and the degree of loss caused by the occurrence of the second medical event, including: Inquiring a first quantized value corresponding to the target event and a second quantized value corresponding to the degree of loss caused by the occurrence of the second medical event in the quantized first dimension and the second dimension; The first quantified value and the second quantified value are calculated to obtain the risk level of the target event.

[0010] In one embodiment, the medical event vulnerability assessment model further includes a pre-set deep neural network, an agent of the deep neural network is set as a medical event, and the agent selects the direction of the development of the medical event as an action during the interactive decision-making process between the agent and the environment, and the decision-making process is a Markov decision obtained by modeling the medical event development task, and the method further includes: The key information of the disease condition and the first medical event are input into the deep neural network, and the neural network is used to predict whether the first medical event will develop into a second medical event.

[0011] In one embodiment, the step of training the deep neural network includes: Collecting different medical event development samples; the medical event development sample records include a third medical event and condition-related information of the third medical event; The agent selects a change in the disease progression direction of the third medical event to obtain a change state; If the distance between the changed state and the at least one final medical event is less than a first preset value, the agent is rewarded.

[0012] In one embodiment, after reporting the target event to the processing port corresponding to the second medical event, the method further includes: The second medical event is displayed on a page corresponding to the second medical event.

[0013] In a second aspect, an embodiment provides a medical vulnerability event reporting device, the device comprising: A detection module, used for detecting the presence of critical information of a disease condition associated with a target event in a first medical event during the process of reading system records, and inputting the critical information of the disease condition into a pre-set medical event vulnerability assessment model; the target event includes the development of the first medical event to a second medical event; A calculation module, used to calculate the target event in a first dimension and a second dimension using the medical event vulnerability assessment model to obtain a calculation result; the first dimension includes the probability of the first medical event developing into the second medical event; the second dimension includes the consequences caused by the first medical event developing into the second medical event; A reporting module is used to report the target event to a processing port corresponding to the second medical event according to the calculation result.

[0014] The beneficial effects of this application are: The embodiment of the present application utilizes a model to automatically extract and analyze data recorded in a medical information system, and calculates the possibility of a medical condition developing into another medical condition under the recorded objective conditions, or the possibility of developing other symptoms, as well as the severity of the consequences caused by the development of the disease, based on the basic information, treatment methods, examination data, etc. about a medical condition recorded in the medical information system. According to the possibility of the development of the disease and the severity of the consequences caused by the development of the disease, it is determined whether the reporting standard of the medical vulnerability event is met. Since the development trend of the disease is predicted, if the medical vulnerability event is reported, it can be directly reported to the personnel who can handle the medical vulnerability event, successfully intervening in the uncontrollable development of the disease, making preparations in advance, and avoiding economic losses caused by further deterioration of the patient's condition. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flowchart of the steps of the medical vulnerability event reporting method proposed in the embodiment of the present application; Figure 2 This is a schematic diagram of quantization values ​​of a first dimension and a second dimension of the present application; Figure 3 It is a functional module diagram of the medical vulnerability event reporting device proposed in the embodiment of the present application. DETAILED DESCRIPTION

[0016] The present application is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are intended to enable the present application to be better understood. However, those skilled in the art can easily recognize that some of the features can be omitted in different situations, or can be replaced by other elements, materials, and methods. In some cases, some operations related to the present application are not shown or described in the specification, in order to avoid the core part of the present application being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations based on the description in the specification and the general technical knowledge in the art.

[0017] In addition, the features, operations or characteristics described in the specification can be combined in any appropriate manner to form various implementations. At the same time, the steps or actions in the method description can also be interchanged or adjusted in a manner that is obvious to those skilled in the art. Therefore, the various sequences in the specification and the drawings are only for the purpose of clearly describing a certain embodiment and are not meant to be a required sequence, unless otherwise specified that a certain sequence must be followed.

[0018] The serial numbers assigned to the components herein, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning. The "connection" and "coupling" mentioned in this application, unless otherwise specified, include direct and indirect connections (couplings).

[0019] Figure 1 is a flowchart of the steps of the medical vulnerability event reporting method proposed in the embodiment of the present application, such as Figure 1 As shown, the steps of the medical vulnerability event reporting method include: S1: In the process of reading system records, it is detected that the first medical event contains key information of the condition associated with the target event, and the key information of the condition is input into a pre-set medical event vulnerability assessment model.

[0020] The target event includes the progression from the first medical event to the second medical event.

[0021] Among them, the first medical event can be understood as the patient's primary condition, and the second medical event is a condition different from the first medical event, or a symptom different from the primary condition.

[0022] For example, the first medical event is "periarthritis of the shoulder", and the relevant information recorded by the medical information system includes: "The patient suffered a pneumothorax on the spot after receiving acupuncture treatment on August 1". After data statistics and model analysis, it was found that: "receiving acupuncture treatment" may be the key information of the disease condition related to the target event, "periarthritis of the shoulder" is the first medical event, and "pneumothorax" is the second medical event.

[0023] For example, the first medical event is "paroxysmal atrial fibrillation and dilated cardiomyopathy". The relevant information recorded by the medical information system includes: "The patient was suspected of having paroxysmal atrial fibrillation and dilated cardiomyopathy. Amiodarone and dopamine were pumped into the left upper limb. Swelling and pain gradually appeared during the dobutamine treatment." After data statistics and model analysis, it was found that: "Amiodarone, dopamine and dobutamine were pumped into the left upper limb" may be the key information of the condition associated with the target event, and "swelling and pain" is the second medical event.

[0024] For example, the first medical event is an "obese patient", and the relevant information recorded by the medical information system includes: "an obese patient who had a stroke, was bedridden, and eventually developed bedsores." After data statistics and model analysis, it was found that: "stroke, bedridden" may be the key medical information associated with the target event, and "bedsores" is the second medical event.

[0025] The embodiment of the present application reads the case records, outpatient records, examination data, medication information, treatment information and other files stored in the medical information system, and automatically captures the key information that may lead to the further development of the first medical event. Then, the key information is analyzed using the pre-set medical event vulnerability assessment model to determine whether the first medical event will develop into other conditions, or other symptoms, or further deteriorate, etc., under the influence of objective factors, treatment methods, basic patient information and other key information.

[0026] The patient's basic information includes information such as age, gender, and underlying diseases.

[0027] S2: Calculate the target event in the first dimension and the second dimension using the medical event vulnerability assessment model to obtain the calculation results.

[0028] The first dimension includes the probability of the first medical event developing into the second medical event; the second dimension includes the consequences caused by the first medical event developing into the second medical event.

[0029] An example of the present application obtains the possibility of a first medical event developing into a second medical event based on the probability of the first medical event developing into a second medical event, determines whether to report a vulnerability event based on the consequences caused by the first medical event developing into the second medical event and the severity of the first medical event developing into the second medical event, and determines based on the possibility of the first medical event developing into the second medical event and the consequences caused by the first medical event developing into the second medical event.

[0030] The greater the possibility that the first medical event will develop into a second medical event, the greater the risk that the first medical event will develop into a vulnerable event based on the records of the medical information system, the greater the loss caused by the consequences of the first medical event developing into the second medical event, and the greater the loss caused by the development of the first medical event. Therefore, the development of the first medical event should be reported to the department that can handle the incident.

[0031] In view of the above objective facts, the present application embodiment provides a method for executing S2: S21: Determine the probability of the target event occurring due to key disease information based on the medical event vulnerability assessment model.

[0032] Before applying the medical event vulnerability assessment model, relevant data samples can be collected in advance to train the medical event vulnerability assessment model. The medical event vulnerability assessment model learns and determines the probability of the target event occurring due to the key information of the disease condition based on the relevant data samples, or can further determine the possibility of the target event occurring due to the key information of the disease condition.

[0033] Alternatively, during the stage of applying the medical event vulnerability assessment model, the vulnerability assessment model can continue to learn information about the development of the first medical event into the second medical event, and adaptively adjust the vulnerability assessment model to make the vulnerability assessment model more robust.

[0034] For example, assume that relevant information records of N patients with "paroxysmal atrial fibrillation and dilated cardiomyopathy" are collected, and N data samples are obtained, of which M samples record the data of "amiodarone, dopamine, and dobutamine pumped into the left upper limb", and M-1 of the M samples record the "swelling and pain symptoms" of the patients, where M is less than N, and NM is less than the constant C. The above samples are used to train the medical event vulnerability assessment model, and the medical event vulnerability assessment model performs statistics and learning on the above sample data. When the data of "paroxysmal atrial fibrillation, dilated cardiomyopathy, amiodarone, dopamine, and dobutamine pumped into the left upper limb" is detected in the application stage, the probability of the target event caused by the key information of the disease is (M-1) / N; or, the medical event vulnerability assessment model can further predict the probability of the target event caused by the key information of the disease as a message that is likely to occur, based on the output probability of the target event occurring being (M-1) / N.

[0035] In one example, the method of determining the probability of a target event occurring within at least one recording period due to critical information of a medical condition based on a medical event vulnerability assessment model further includes the steps of: If the average probability is found in the medical event vulnerability assessment model to be lower than the first preset threshold and greater than the third preset threshold, the average probability is increased to exceed the first preset threshold.

[0036] In order to more comprehensively prevent the occurrence of medical vulnerability events, the probability of the target event occurring can be increased based on the average probability of the target event occurring calculated by the medical event vulnerability assessment model.

[0037] For example, suppose the medical event vulnerability assessment model outputs the risk of "obese patient with stroke, bedridden" eventually developing bedsores. S22: Determine the extent of loss caused by the occurrence of the second medical event based on the medical event vulnerability assessment model.

[0038] Before applying the medical event vulnerability assessment model, relevant data samples can be collected in advance. The relevant data samples can further include marked loss values, which can be manually confirmed. The medical event vulnerability assessment model is trained using the relevant data samples. The medical event vulnerability assessment model learns the degree of loss that may be caused by the occurrence of the target event based on the relevant data samples.

[0039] A deep neural network can be constructed in the medical event vulnerability assessment model, which is used to train the neural network using a supervised learning method according to the operating methods corresponding to the second medical event, the drugs used to treat the second medical event, the direct losses caused by the second medical event, and the manually marked loss values. After learning, the neural network can estimate the economic value of the target event cost based on the direct losses, the drugs used to treat the second medical event, and the operating methods corresponding to the second medical event, and then adjust the deep neural network based on the gap between the economic value and the marked loss value, and finally obtain a loss degree prediction model that can output the loss degree based on the direct losses, the drugs used to treat the second medical event, and the operating methods corresponding to the second medical event.

[0040] Determine the extent of loss caused by the second medical event based on the medical event vulnerability assessment model, including: S201: Find the direct loss corresponding to the occurrence of the target event in the medical event vulnerability assessment model, or / and query the operation means corresponding to the second medical event.

[0041] During the training phase, the direct losses corresponding to the occurrence of the target event can be obtained, and / or the operating methods corresponding to the second medical event can be queried. Relevant data can also be extracted from the medical information system: the operating methods corresponding to the second medical event, the drugs used to treat the second medical event, and the direct losses caused by the occurrence of the second medical event.

[0042] S202: Analyze the consequences to obtain direct losses caused by the second medical event, obtain the degree of loss, and / or calculate the degree of loss corresponding to the operation means.

[0043] For example, suppose that relevant information records of N patients with "paroxysmal atrial fibrillation and dilated cardiomyopathy" are collected, and N data samples are obtained, of which M samples record the data of "amiodarone, dopamine and dobutamine pumped into the left upper limb", and M-1 of the M samples record the "swelling and pain symptoms" of the patients, where M is less than N, and NM is less than the constant C, and each of the M-1 samples carries a label-loss value T. The above samples are used to train the medical event vulnerability assessment model, which performs statistics and learning on the above sample data. After learning the relationship between the loss value and the first medical event, the second medical event, and the key information, it has the ability to infer the degree of loss caused by swelling and pain in patients with paroxysmal atrial fibrillation and dilated cardiomyopathy.

[0044] S23: If the probability of the target event occurring due to the key disease information output by the vulnerability assessment model is greater than the first preset threshold, the target event is reported to the second medical event corresponding processing port.

[0045] S24: If the degree of loss caused by the occurrence of the second medical event output by the vulnerability assessment model is greater than the second preset threshold, the target event is reported to the processing port corresponding to the second medical event.

[0046] S3: According to the calculation result, the target event is reported to the processing port corresponding to the second medical event.

[0047] In one example, the processing port corresponding to the second medical event is connected to the storage area called when the second medical event handler's operation interface is running. The system detects that the second medical event handler has logged into the system and calls the operation file stored in a specific storage area when generating the operation interface. The processing port corresponding to the second medical event is connected to the specific storage area. Therefore, the system detects that the second medical event handler has logged into the system and can display the target event of the first medical event developing into the second medical event. Since the second medical event handler can directly handle the second medical event, compared to notifying the person who handles the first medical event or notifying the functional department, the embodiment of the present application reports the event to the processing port corresponding to the second medical event and directly reports the event to the person who can handle the event, thereby reducing the time consumed in the message forwarding process and improving the efficiency of vulnerability event handling.

[0048] Therefore, after reporting the target event to the second medical event corresponding processing port, the method further includes: The second medical event is displayed on a page corresponding to the second medical event to notify relevant personnel to handle the target event.

[0049] The second medical event display method includes images, texts, icons, etc.

[0050] The embodiment of the present application utilizes a model to automatically extract and analyze data recorded in a medical information system, and calculates the possibility of a medical condition developing into another medical condition under the recorded objective conditions, or the possibility of developing other symptoms, as well as the severity of the consequences caused by the development of the disease, based on the basic information, treatment methods, examination data, etc. about a medical condition recorded in the medical information system. According to the possibility of the development of the disease and the severity of the consequences caused by the development of the disease, it is determined whether the reporting standard of the medical vulnerability event is met. Since the development trend of the disease is predicted, if the medical vulnerability event is reported, it can be directly reported to the personnel who can handle the medical vulnerability event, successfully intervening in the uncontrollable development of the disease, making preparations in advance, and avoiding economic losses caused by further deterioration of the patient's condition.

[0051] In order to comprehensively consider the impact of two factors on whether to report the target event, another embodiment of the present application also proposes a method of executing S2; the two factors are the possibility of the first medical event developing into the second medical event, and the degree of loss caused by the consequences of the first medical event developing into the second medical event.

[0052] After obtaining the probability of the target event occurring and the degree of loss caused by the second medical event, the risk level of the target event can be calculated based on the probability of the target event occurring and the degree of loss caused by the second medical event, and then the method of reporting the target event can be determined based on the risk level.

[0053] S2-1: Determine the probability of the target event occurring due to the key information of the disease based on the medical event vulnerability assessment model; S2-2: Determine the extent of loss caused by the occurrence of the second medical event based on the medical event vulnerability assessment model; S2-3: Predict the risk level of the target event based on the probability of the target event occurring and the extent of the loss caused by the second medical event.

[0054] A method of executing step S2-3 to predict the risk level of the target event includes: S301: quantifying the first dimension and the second dimension according to the development records of different medical events stored in the medical event vulnerability assessment model.

[0055] During the data collection stage, manual labeling can be used to quantify the first and second dimensions of specific events.

[0056] For example, there are N records about the first medical event "obese stroke patient", and M records of "obese stroke patient, bedridden, and eventually developed bedsores". The probability of obesity due to stroke developing into bedsores is calculated to be M / N. Based on the basic probability, the first dimension is quantified. The record of "obese stroke patient, bedridden, and eventually developed bedsores" records the corresponding economic losses. The second dimension is quantified based on the average economic loss.

[0057] S302: Querying a first quantitative value corresponding to the target event and a second quantitative value corresponding to the degree of loss caused by the occurrence of a second medical event in a risk consequence quantitative matrix.

[0058] S303: Calculate the first quantization value and the second quantization value to obtain the risk level of the target event.

[0059] Figure 2 This is a schematic diagram of the quantization value of the first dimension and the second dimension of the present application, such as Figure 2 As shown, in the application stage, according to the loss degree of the target event and the probability of the target event, the probability of the target event in the first dimension increases from the starting point, and the severity in the second dimension increases from the starting point. Figure 2 Find the corresponding value point in the , and use the risk level corresponding to the value point as the risk level of the target event. For example, the probability of "an obese stroke patient, bedridden, and eventually develops bedsores" is P, and the degree of loss is Q. Figure 2 Find the point B corresponding to the probability P and the degree of loss Q. The risk level corresponding to point B is H. It can be determined that the risk level of "an obese stroke patient who is bedridden and eventually develops bedsores" is H. Figure 2 E indicates extreme risk and needs to be reported immediately; H indicates high risk and needs to be reported to senior management; M indicates medium risk and needs to be reported to relevant personnel; and L indicates low risk and does not need to be reported for the time being.

[0060] The present application also proposes a method for implementing a medical event vulnerability assessment model to predict a target event: Another deep neural network is constructed in the medical event vulnerability assessment model, and the deep neural network is trained by reinforcement learning. The medical event is set as the intelligent agent, the possible development direction of the medical event is used as the action, the action space is constructed, and the state of the medical event development is used as the state space. All sample data, action space, and state space uploaded to the medical event vulnerability assessment model constitute the learning environment of the intelligent agent. For example, sample data may include but are not limited to: "The patient is considered to have paroxysmal atrial fibrillation and dilated cardiomyopathy. Amiodarone and dopamine are pumped into the left upper limb. Swelling and pain gradually appear during dobutamine", "Obese stroke patient, bedridden, and finally developed bedsores", "Patient with periarthritis of shoulder suffered pneumothorax on the spot after receiving acupuncture treatment on August 1", etc.

[0061] The intelligent agent learns that the current state is paroxysmal atrial fibrillation. Based on the decision function, it selects an action in the action space: execute steps in the direction of developing into pneumothorax, calculates the distance between the state of the intelligent agent at this time and the final medical event "pneumothorax" to be reduced to below the first preset value, and rewards the intelligent agent, so that the intelligent agent learns the development direction of the disease.

[0062] At the same time, after the intelligent agent selects an action in the action space, the selection probability of selecting the action is calculated. After the intelligent agent develops into a state with the smallest distance from the final medical event based on the action, the distance between the selection probability and the calibration probability is calculated. If the distance between the selection probability and the calibration probability is less than a second preset threshold, the intelligent agent is rewarded.

[0063] The calibration probability can be obtained in the manner of other embodiments of the present application by collecting relevant information records of N patients with "paroxysmal atrial fibrillation and dilated cardiomyopathy" to obtain N data samples, of which M samples record the data of "amiodarone, dopamine and dobutamine pumped into the left upper limb", and M-1 of the M samples record the occurrence of "swelling and pain symptoms" in patients, where M is less than N, and NM is less than the constant C, and the calibration probability is calculated.

[0064] The intelligent agent in the trained deep neural network can automatically simulate the development of the disease according to the environment, thereby predicting whether the first medical event will develop into a second medical event.

[0065] The medical event vulnerability assessment model also includes a pre-set deep neural network, and the intelligent agent of the deep neural network is set as a medical event. In the interactive decision-making process between the intelligent agent and the environment, the direction of the development of the medical event is selected as an action. The decision-making process is a Markov decision obtained by modeling the medical event development task. The method also includes: The key information of the disease and the first medical event are input into the deep neural network, and the neural network is used to predict whether the first medical event will develop into the second medical event.

[0066] The key information of the first medical event and the condition of the related target event is input into a medical event vulnerability assessment model embedded in a deep neural network that has undergone reinforcement learning. The medical event vulnerability assessment model can output the development result of the first medical event. If the first medical event develops into other conditions, or the first medical event develops other symptoms, it is determined that the first medical event develops into a second medical event.

[0067] The process of training the medical event vulnerability assessment model using reinforcement learning includes: S401: Collect different medical event development samples; the medical event development sample records include the third medical event and the condition-related information of the third medical event; The third medical event refers to the final state of the development of the first medical event in the sample.

[0068] For example: "The patient was suspected of having paroxysmal atrial fibrillation and dilated cardiomyopathy. Amiodarone and dopamine were pumped into the left upper limb. Swelling and pain gradually appeared during the dobutamine treatment", "An obese patient with a stroke was bedridden and eventually developed bedsores."

[0069] S402: The agent selects a change in the disease development direction of the third medical event and obtains a change state; S403: If the distance between the changed state and at least one final medical event is less than a first preset value, the agent is rewarded.

[0070] Figure 3 is a functional module diagram of a medical vulnerability event reporting device proposed in an embodiment of the present application, such as Figure 3 As shown, the medical vulnerability event reporting device includes: The detection module 31 is used to detect the presence of key information of the disease condition associated with the target event in the first medical event during the process of reading the system record, and input the key information of the disease condition into a pre-set medical event vulnerability assessment model; the target event includes the development of the first medical event to the second medical event; The calculation module 32 is used to calculate the target event in the first dimension and the second dimension using the medical event vulnerability assessment model to obtain a calculation result; the first dimension includes the probability of the first medical event developing into the second medical event; the second dimension includes the consequences caused by the first medical event developing into the second medical event; The reporting module 33 is used to report the target event to the second medical event corresponding processing port according to the calculation result.

[0071] Figure 3 The implementation principle and technical effects of the medical vulnerability event reporting device provided in the illustrated embodiment may be further referred to the relevant description in the medical vulnerability event reporting method embodiment.

[0072] Optionally, the calculation module includes: The probability calculation submodule is used to determine the probability of the target event occurring due to the key information of the disease based on the medical event vulnerability assessment model; A loss calculation submodule, used to determine the extent of loss caused by the occurrence of the second medical event based on the medical event vulnerability assessment model; The reporting module is specifically used to report the target event to the corresponding processing port of the second medical event if the probability of the target event occurring due to the key information of the medical condition is greater than the first preset threshold; if the degree of loss caused by the occurrence of the second medical event is greater than the second preset threshold, the target event is reported to the corresponding processing port of the second medical event.

[0073] Optionally, the probability calculation submodule is specifically used to increase the average probability to exceed the first preset threshold if the average probability is found to be lower than a first preset threshold and greater than a third preset threshold in the medical event vulnerability assessment model.

[0074] Optionally, the calculation module includes: The probability calculation submodule is used to determine the probability of the target event occurring due to the key information of the disease based on the medical event vulnerability assessment model; A loss calculation submodule, used to determine the extent of loss caused by the occurrence of the second medical event based on the medical event vulnerability assessment model; A risk level calculation submodule is used to predict the risk level of the target event based on the probability of the target event occurring and the degree of loss caused by the occurrence of the second medical event; The reporting module is specifically used to report the target event to the second medical event corresponding processing port according to the risk level.

[0075] Optionally, the risk level calculation submodule is specifically used to find the direct calculation corresponding to the occurrence of the target event in the medical event vulnerability assessment model, or / and query the operation means corresponding to the second medical event; Calculate the degree of loss corresponding to the operating means.

[0076] Optionally, the medical vulnerability event reporting device further includes: a quantification module, for quantifying the first dimension and the second dimension according to the development records of different medical events stored in the medical event vulnerability assessment model; The risk level calculation submodule is specifically used to query the first quantized value corresponding to the target event in the quantized first dimension and the second dimension, and the second quantized value corresponding to the degree of loss caused by the occurrence of the second medical event; The first quantitative value and the second quantitative value are calculated to obtain the risk level of the target event.

[0077] Optionally, the medical event vulnerability assessment model further includes a pre-set deep neural network, the agent of the deep neural network is set as a medical event, the direction of the development of the medical event is selected as an action in the interactive decision-making process between the agent and the environment, and the decision-making process is a Markov decision obtained by modeling the medical event development task. The device also includes: The prediction module is used to input key information of the disease condition and the first medical event into the deep neural network of the medical vulnerability event, and use the neural network to predict whether the first medical event will develop into a second medical event.

[0078] Optionally, the medical vulnerability event reporting device further includes a module for training a deep neural network, which is used to collect different medical event development samples; the medical event development sample record includes a third medical event and condition-related information of the third medical event; The agent selects the change in the disease development direction of the third medical event and obtains the change state; If the distance between the changed state and at least one final medical event is less than a first preset value, the agent is rewarded.

[0079] Optionally, medical vulnerability event reporting may also include: The display module is used to display the second medical event on a page corresponding to the second medical event.

[0080] Regarding the various modules / units included in the various devices described in the above embodiments, they can be software modules / units, or hardware modules / units, or they can be partially software modules / units and partially hardware modules / units. For example, for various devices applied to or integrated in a chip, the various modules / units included therein can all be implemented in the form of hardware such as circuits, or at least some of the modules / units can be implemented in the form of software programs, which run on a processor integrated inside the chip, and the remaining modules / units can be implemented in the form of hardware such as circuits; for various devices applied to or integrated in a chip module, the various modules / units included therein can all be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component of the chip module (such as a chip, circuit module, etc.) or in different components, or at least some of the modules / units can be implemented in the form of software programs. The software program may be implemented in the form of a program, which runs on a processor integrated in the chip module, and the remaining modules / units may be implemented in the form of hardware such as circuits; for each device applied to or integrated in the electronic terminal device, each module / unit contained therein may be implemented in the form of hardware such as circuits, and different modules / units may be located in the same component (for example, a chip, a circuit module, etc.) or in different components in the electronic terminal device, or at least some modules / units may be implemented in the form of a software program, which runs on a processor integrated in the electronic terminal device, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits.

[0081] In one embodiment of the present application, a computer-readable storage medium is provided, on which a program is stored. The stored program includes a method that can be loaded by a processor and process any of the above embodiments.

[0082] Those skilled in the art will appreciate that all or part of the functions of the various methods in the above-mentioned embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to implement the above-mentioned functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the above-mentioned functions can be implemented. In addition, when all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can also be stored in a storage medium such as a server, another computer, disk, optical disk, flash disk or mobile hard disk, and can be downloaded or copied and saved in the memory of the local device, or the system of the local device is updated, and when the program in the memory is executed by the processor, all or part of the functions in the above-mentioned embodiments can be implemented.

[0083] The above specific examples are used to illustrate the present application, which is only used to help understand the present application and is not intended to limit the present application. For technicians in the technical field to which the present application belongs, they can also make some simple deductions, deformations or substitutions based on the ideas of the present application.

Claims

1. A method for reporting medical vulnerability events, characterized in that: The method comprises: In the process of reading the system records, it is detected that there is key information of the condition associated with the target event in the first medical event, and the key information of the condition is input into a pre-set medical event vulnerability assessment model; the target event includes the development of the first medical event to the second medical event; The target event is calculated using the medical event vulnerability assessment model in a first dimension and a second dimension to obtain a calculation result; the first dimension includes the probability of the first medical event developing into the second medical event; the second dimension includes the consequences caused by the first medical event developing into the second medical event; According to the calculation result, the target event is reported to the processing port corresponding to the second medical event.

2. The method for reporting medical vulnerability events according to claim 1, characterized in that: The target event is calculated using the medical event vulnerability assessment model in the first dimension and the second dimension to obtain a calculation result, including: Determining the probability of the target event occurring due to the key disease information based on the medical event vulnerability assessment model; Determining the extent of loss caused by the occurrence of the second medical event based on the medical event vulnerability assessment model; According to the calculation result, reporting the target event to a processing port corresponding to the second medical event includes: If the probability of the target event occurring due to the critical disease information is greater than a first preset threshold, reporting the target event to the second medical event corresponding processing port; If the degree of loss caused by the occurrence of the second medical event is greater than a second preset threshold, the target event is reported to the processing port corresponding to the second medical event.

3. The method for reporting medical vulnerability events according to claim 2, characterized in that: Determining the probability of the target event occurring within at least one recording period due to the key condition information based on the medical event vulnerability assessment model includes: If it is found in the medical event vulnerability assessment model that the average probability is lower than the first preset threshold and greater than the third preset threshold, the average probability is increased to exceed the first preset threshold.

4. The method for reporting medical vulnerability events according to claim 1, characterized in that: The target event is calculated using the medical event vulnerability assessment model in the first dimension and the second dimension to obtain a calculation result, including: Determining the probability of the target event occurring due to the key disease information based on the medical event vulnerability assessment model; Determining the extent of loss caused by the occurrence of the second medical event based on the medical event vulnerability assessment model; Predicting the risk level of the target event according to the probability of the target event occurring and the extent of the loss caused by the occurrence of the second medical event; According to the calculation result, reporting the target event to a processing port corresponding to the second medical event includes: According to the risk level, the target event is reported to the processing port corresponding to the second medical event.

5. The medical vulnerability event reporting method according to claim 4 or 2, characterized in that: Determining the extent of loss caused by the occurrence of the second medical event based on the medical event vulnerability assessment model includes: Finding the direct calculation corresponding to the occurrence of the target event in the medical event vulnerability assessment model, or / and querying the operation means corresponding to the second medical event; Calculate the degree of loss corresponding to the operation means.

6. The method for reporting medical vulnerability events according to claim 4, characterized in that: Before predicting the risk level of the target event based on the probability of the target event occurring within at least one recording period and the degree of loss caused by the occurrence of the second medical event, the method further includes: quantifying the first dimension and the second dimension according to development records of different medical events stored in the medical event vulnerability assessment model; Predicting the risk level of the target event according to the probability of the target event occurring and the degree of loss caused by the occurrence of the second medical event, including: Inquiring a first quantized value corresponding to the target event and a second quantized value corresponding to the degree of loss caused by the occurrence of the second medical event in the quantized first dimension and the second dimension; The first quantified value and the second quantified value are calculated to obtain the risk level of the target event.

7. The method for reporting medical vulnerability events according to claim 2, characterized in that: The medical event vulnerability assessment model also includes a pre-set deep neural network, and the agent of the deep neural network is set as a medical event. The agent selects the direction of the development of the medical event as an action during the interactive decision-making process between the agent and the environment. The decision-making process is a Markov decision obtained by modeling the medical event development task. The method also includes: The key information of the disease condition and the first medical event are input into the deep neural network, and the neural network is used to predict whether the first medical event will develop into a second medical event.

8. The method for reporting medical vulnerability events according to claim 7, characterized in that: The steps of training the deep neural network include: Collecting different medical event development samples; the medical event development sample records include a third medical event and condition-related information of the third medical event; The agent selects a change in the disease progression direction of the third medical event to obtain a change state; If the distance between the changed state and the at least one final medical event is less than a first preset value, the agent is rewarded.

9. The method according to claim 1, characterized in that: After reporting the target event to the processing port corresponding to the second medical event, the method further includes: The second medical event is displayed on a page corresponding to the second medical event.

10. A medical vulnerability event reporting device, characterized in that: The medical vulnerability event reporting device comprises: A detection module, used for detecting the presence of critical information of a disease condition associated with a target event in a first medical event during the process of reading system records, and inputting the critical information of the disease condition into a pre-set medical event vulnerability assessment model; the target event includes the development of the first medical event to a second medical event; A calculation module, used to calculate the target event in a first dimension and a second dimension using the medical event vulnerability assessment model to obtain a calculation result; the first dimension includes the probability of the first medical event developing into the second medical event; the second dimension includes the consequences caused by the first medical event developing into the second medical event; A reporting module is used to report the target event to a processing port corresponding to the second medical event according to the calculation result.

Images